CN100418090C - Data storage method and data storage structure - Google Patents

Data storage method and data storage structure Download PDF

Info

Publication number
CN100418090C
CN100418090C CN 200510097937 CN200510097937A CN100418090C CN 100418090 C CN100418090 C CN 100418090C CN 200510097937 CN200510097937 CN 200510097937 CN 200510097937 A CN200510097937 A CN 200510097937A CN 100418090 C CN100418090 C CN 100418090C
Authority
CN
Grant status
Grant
Patent type
Prior art keywords
data
storage
method
structure
data storage
Prior art date
Application number
CN 200510097937
Other languages
Chinese (zh)
Other versions
CN1924851A (en )
Inventor
博哈弗施·德汉吉·巴德哈博哈蒂
林咏华
武·丁·奇恩
王艳琦
Original Assignee
国际商业机器公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Grant date

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/30Information retrieval; Database structures therefor ; File system structures therefor
    • G06F17/30943Information retrieval; Database structures therefor ; File system structures therefor details of database functions independent of the retrieved data type
    • G06F17/30946Information retrieval; Database structures therefor ; File system structures therefor details of database functions independent of the retrieved data type indexing structures
    • G06F17/30952Information retrieval; Database structures therefor ; File system structures therefor details of database functions independent of the retrieved data type indexing structures using directory or table look-up
    • G06F17/30955Information retrieval; Database structures therefor ; File system structures therefor details of database functions independent of the retrieved data type indexing structures using directory or table look-up using more than one table in sequence, i.e. systems with three or more layers

Abstract

本申请提供了一种数据存储方法,根据本发明的一个方面,提供了一种存储数据的方法,包括如下步骤:在第一存储区设置一个第一数据节点;在第二存储区设置一个第二数据节点;其中,所述第二数据节点是构成第二存储区中至少一个平表中的一个第一平表的多个元素中的一个元素;并且,所述设置第一数据节点的步骤包括在该节点中存储一个链接二元组,其包括一个表示所述第一平表的第一标识符和一个表示所述元素在第一平表中所处的行的第二标识符。 The present application provides a data storage method, according to one aspect of the invention, there is provided a method of storing data, comprising the steps of: providing a first node in a first data storage area; providing a second memory area in the second second data node; wherein the second data node of said plurality of elements constituting a second storage area in at least a meter in a first flat table; and, said step of setting first data node storing tuples comprises a link in the node, which represents the first identifier comprising a first level and a table showing the identifier of the second element is located in the first row of the table level. 根据本发明的另一个方面,还提供了一种相应的数据存储结构。 According to another aspect of the present invention, there is also provided a corresponding data storage structure. 根据本发明,可以在不支持存储地址指针的特定目的处理器中容易地实现数据链接,从而降低对存储数据所需的空间要求并且提高链接各个数据段的效率。 According to the present invention, can be easily implemented in a data link does not support a particular memory address pointers purpose processor, thereby reducing the space required to store data needed to improve the efficiency of the link and the respective data segment.

Description

一种存储数据的方法技术领域本发明涉及一种数据存储方法和数据存储结构,更具体地,本发明涉及一种用于不支持指针的特定目的处理器的数据存储方法和数据存储结构。 TECHNICAL FIELD The present invention is for storing data directed to a data storage method and the data storage structure, and more particularly, the present invention relates to a method and a data storage structure for storing data for a particular purpose processor does not support a pointer. 背景技术特定目的处理器是特别为一些特定应用而设计的高性能的处理器,例如,数学处理器,用作通用处理器的协处理器,并执行数学运算;网络处理器,用来处理网络业务(即交换机,路由器等)等等。 BACKGROUND specific-purpose processor is a high performance processor specifically designed for specific applications, e.g., math processor, a coprocessor is used as a general purpose processor, and performing mathematical operations; network processor for processing network service (i.e., switches, routers, etc.) and the like. 因此,由于其用于特定的应用,特定目的处理器必须牺牲一些灵活性而来实现其特殊功能。 Therefore, since for a particular application, specific purpose processors must sacrifice some flexibility from achieving its special features. 一般地,特定目的处理器采用一些高性能的硬件引擎,其中每个硬件引擎设计成用来支持特定的功能,例如队列管理、表查询、存储器访问等。 Generally, the specific object of some high-performance processor hardware engine, wherein each of the hardware engines designed to support specific functions, such as queue management, query, a memory access. 为了实现较高的性能,特定目的处理器经常利用与常规存储器体系(例如,主存储器、高速緩冲存储器等)不同的存储器结构。 To achieve high performance, specific purpose processors often use with conventional memory system (e.g., main memory, cache memory, etc.) of different memory structures. 在特定目的处理器中,存储器通常分为控制存储器和数据存储器,其中控制存储器中包括用于数据处理的主信息,而数据存储器中包括伴随处理请求的数据。 In a particular purpose processor, the memory is usually divided into control and data memory, wherein the memory comprises the control information for the primary data processing, the data memory comprises a data processing request is accompanied. 在使用至少一个搜索引擎的特定目的处理器中,为了快速查询, 可以采用索引表。 In a particular purpose processor uses at least one search engine in order to quickly find, you can use the index table. 因此,在这样的特定目的处理器中,至少支持两种表:索引表和平表(flat table)。 Therefore, in such a specific purpose processors, supports at least two tables: Table index peace table (flat table). 索引表可以用索引树来实现。 Index table with index tree can be achieved. 索引树是由n(nX))个结点组成的有限集合。 Index tree is a finite set of n (nX)) nodes thereof. 索引树包括根结点、 叶结点(终端结点)以及非终端结点。 Index tree comprising a root node, leaf nodes (terminal node) and a non-terminal node. 一般在叶结点中存储相关的信息。 General information stored in the leaf node associated. 从索引树的根结点到叶结点的路径由索引表中的关键码标识。 Index tree from the root node to the leaf node identified by the route key in the index table. 用户可以通过索引树的标识符和关键码,并触发表查询(索引树搜索)命令,访问索引表。 Users can identifier and the key index tree, and trigger table query (the index tree search) command, access the index table. 搜索的等持时间取决于关键码的长度和索引树的结构。 And other key holding time depends on the length and structure of the search of the index tree. 平表可以用存储器阵列来实现。 Level meter can be used to achieve a memory array. 存储器阵列的一行或一列可以存储一个平表的一行(元素)。 Row of the memory array may store one or a flat table row (of elements). 在数据处理中,数据链接能使数据在逻辑上更合理地链接在一起,这样能够在保持数据完整性的前提下降低对存储单元的空间要求。 In data processing, the data link enables more rational data are logically linked together, so that space can be reduced in the memory cell holding the data integrity requirements of the premise. 数据处理的软件设计的灵活性,在很大程度上取决于作为数据链接的单一且简单的机制的单一指针。 Data processing software design flexibility, depends largely on a single data link pointer as a single and simple mechanism. 由于用于特定应用的原因,特定目的处理器通常不支持通过指针(存储位置的地址)对存储器的访问,从而不具备通过单一指针来进行数据链接的能力。 Reasons for a particular application, specific purpose processors typically does not support a pointer (address storage location) access to the memory so as not to have the capability to perform the data link by a single pointer. 缺少这样的单一指针将会使得不能容易地实现数据链接,软件设计的灵活性将变得较差。 The lack of such a single indicator will make it impossible to easily achieve data links, software design flexibility will become poor. 而由于叶结点的容量有上限,能够存储在一个叶结点中的信息的容量也受到限制。 Since the leaf node has the capacity limit, the capacity of information can be stored in a leaf node is also limited. 难以满足某些复杂的应用中(例如在网络通信中涉及的隧道应用等)的需求。 Difficult to meet some complex applications (e.g., in a tunnel application relates to network communications, etc.) requirements. 因此,存在扩展诸如叶节点的信息容量的需要。 Accordingly, there is need to expand the capacity of information such as a leaf node. 然而,由于特定目的处理器不具备通过单一指针来进行数据链接的能力,数据链接的效率低,因此存在数据大与数据存储单元容量小的矛盾。 However, since the specific purpose processors do not have the ability to perform the data link by a single pointer, the low efficiency of the data link, the data storage unit with a large data capacity is small there is contradiction. 发明内容本发明的一个目的在于提供一种数据存储方法和数据存储结构, 其可以使特定目的处理器容易地实现数据链接,扩展数据节点的存储容量。 SUMMARY OF THE INVENTION An object of the present invention to provide a data storage method and the data storage structure, which allows to easily realize the specific purpose data link processor, expand the data storage capacity of the node. 根据本发明的一个方面,提供了一种存储数据的方法,包括如下步骤:在第一存储区设置一个第一数据节点; 在第二存储区设置一个第二数据节点;其中,所述第二数据节点是构成第二存储区中至少一个平表中的一个第一平表的多个元素中的一个元素;并且,所述设置第一数据节点的步骤包括在该节点中存储一个链接二元组,其包括一个表示所述第一平表的第一标识符和一个表示所述元素在第一平表中所处的行的第二标识符。 According to one aspect of the present invention, there is provided a method of storing data, comprising the steps of: providing a first node in a first data storage area; providing a second node in the second data storage area; wherein said second data node is a plurality of elements constituting the second storage area in at least a meter in a first flat table; and, the step of setting said first data stored in the node comprises a node link two yuan group, which represents the first identifier comprising a first level and a table showing the identifier of the second element is located in the first row of the table level. 根据本发明的另一个方面,还提供了一种数据存储结构,包括:在第一存储区设置的第一数据节点;在第二存储区设置的第二数据节点;其中,所述第二数据节点是构成至少一个平表中的一个第一平表的多个元素中的一个元素;并且,所述第一数据节点包含一个链接二元组,其包括一个表示第一平表的第一标识符和一个表示所述元素在第一平表中所处的行的第二标识符。 According to another aspect of the present invention, there is provided a data storage structure, comprising: a first data storage area arranged in a first node; a second node in the second data storage area provided; wherein said second data node is a plurality of elements constituting the at least one flat table a first flat table; and, said first node comprises a data link tuple, which represents a first identifier comprising a first flat table and a symbol representing a second identifier of the first planar element in which the table rows. 根据本发明,可以在不支持存储地址指针的特定目的处理器中, 通过链接二元组(two-tuple linker),容易地实现数据链接。 According to the present invention, may not support the specific object storage address pointer processor by link tuple (two-tuple linker), the data link easily realized. 例如,在平表形式的存储体系结构中,每个平表由一个表标识符标识,平表中的每一行由相应的元素标识符标识。 For example, the memory architecture in the form of a flat table, each table consists of a table level identifier identifies each row in the table level identifier identifies the corresponding elements. 本发明通过链接二元组中的平表标识符和元素标识符实现与作为平表中的元素的数据节点或存储单元的链接,从而降低对存储数据的特定存储单元或数据节点的空间要求,并且提高链接各个数据的效率。 The present invention is implemented as the link data and node elements or storage units flat table by a flat table identifier and the link identifier tuple element, thereby reducing the storage space of the data storage unit or data node specific requirements, and improve the efficiency of various data links. 通过以下结合附图所作的描述,本发明的其他特点和优点将显而易见,其中在其全部附图中相同标号指示相同或类似部分。 The following description taken in conjunction with the accompanying drawings Other features and advantages of the invention will become apparent in the entire drawings wherein like numerals indicate the same or like parts. 附图说明所附权利要求书阐述了被认为是本发明之特征的新颖特征。 BRIEF DESCRIPTION set forth in the appended claims are believed to be characteristic of the novel features of the present invention. 然而,通过连同附图一起阅读说明性的实施方式的下述详细描述,将更好地理解该发明本身、其优选使用方式、其它目的及其优点,其中:图1是根据本发明的一个实施方式的数据存储方法的流程图;图2是根据本发明的另一个实施方式的数据存储结构的示意图;图3是根据本发明的再一个实施方式数据存储结构的示意图。 However, through detailed description in conjunction with the accompanying drawings of illustrative embodiments with the following, the invention will be better understood by itself, preferred mode of use, further objects and advantages thereof, wherein: FIG 1 is an embodiment of the present invention flowchart of a data storage method embodiment; FIG. 2 is a schematic view of another embodiment of the data storage structure of the embodiment of the present invention; FIG. 3 is a schematic diagram of another embodiment of the present invention a data storage structure of the embodiment. 具体实施方式通过参考附图,能更好地理解本发明的优选实施方式及其优点。 DETAILED DESCRIPTION By reference to the drawings, preferred embodiments will be better understood and its advantages embodiment of the present invention. 下面的讨论中,给出了多种特定细节以辅助对本发明的全面理解。 The following discussion, numerous specific details are given to assist in a comprehensive understanding of the present invention. 但是,本领域的技术人员会理解,不需要这些特定的细节也可以实现本发明。 However, those skilled in the art will appreciate that these specific details are not required according to the present invention may be practiced. 在对实施方式的描述中,以概图或框图的形式示出众所周知的部件,以避免不必要的细节使本发明变得难以理解。 In the description of the embodiment, or in the form of a block diagram overview of the illustrated components are well known, so as to avoid unnecessary detail of the present invention is difficult to understand. 为了解决特定目的处理器不能通过指针进行数据链接的问题,根据本发明的一个实施方式,提出了一种采用链接二元组进行数据链接的方案,以便在不支持指针的特定目的处理器中方便地实现数据链接的功能。 In order to address a specific purpose processor can not issue data link pointer, according to one embodiment of the present invention proposed a link using the data link tuple scheme, in order to facilitate a particular object of the pointers in the processor does not support realize the function of the data link. 具体地说,就是将需要存储到一个数据存储结构中的一个数据分割成多个数据段,将每一个数据段存储到一个能够容纳该数据段的存储单元中,并且相应地在该存储单元中存储一个链接二元组。 Specifically, the need is stored in a data storage a data structure divided into a plurality of data segments, each data segment stored in a memory unit capable of receiving the data segment, and correspondingly in the storage unit storing a link tuple. 通过该链接二元组,能够将该存储单元中所存储的数据段与另一个存储单元中所存储的下一个数据段链接在一起。 This link tuple next data segment the data segment can be linked to another storage unit stored in the storage unit stored together. 图1示出了根据本发明的一个实施方式的数据存储方法。 FIG 1 shows a data storage method according to an embodiment of the present invention. 如图1 所示,该数据存储方法包括如下步骤:将一个需要存储到一个数据存储结构中的数据分割成多个数据段(步骤SllO);将所述多个数据段分别存储到多个存储单元中(步骤S120);在除用于存储最后一个数据段的存储单元之外的所述多个存储单元中分别存储一个链接二元组(步骤S130),使得通过该链接二元组,能够将一个存储单元中所存储的一个数据段与另一个存储单元中所存储的下一个数据段链接在一起。 As shown, the data storage method comprising the steps of 1: a need to store data into a data storage structure into a plurality of segments of data (step SllO); said plurality of data segments are stored in the plurality of storage unit (step S120); tuple store a link (step S130) in addition to said plurality of memory cells for storing the last data unit stored in the segment, such that the link through-tuple, can be the next data segment a data segment stored in a storage unit in another storage unit and stored in the linked. 换句话说,所存储的链接二元组指向下一个数据段。 In other words, the stored tuple link points to the next data segment. 当然,也可以在一个存储单元中存储一个链接二元组,使其指向第一个数据段,该存储单元中不存储任何数据段。 Of course, a link may be stored in a tuple memory unit, to point to the first data segment, the memory cell does not store any data segment. 借助于各个数据段的链接,用于存储各个数据段的存储单元在逻辑上也被链接在一起。 By means of a link of the respective data segments, each data storage unit for storing logically segments are also linked together. 在这个存储单元链中,除最后一个存储单元只存储最后一个数据段之外,其它存储单元均存储一个数据段和一个链接二元组。 In this storage unit chain except the last memory cell stores only the last data segment, other memory cells are stored in a data segment and a link tuple. 当然也可以仅在第一个存储单元中存储第一链接二元组,而将第一数据段存储到第二存储单元中。 Of course, the first link may be stored only in the first tuple of the storage unit, and the first data segments stored in the second storage unit. 在这种情况下,第一存储单元仅存储第一链接二元组,最后一个存储单元仅存储最后一个数据段,其它存储单元中均存储一个数据段和一个链接二元组。 In this case, the first storage unit stores only the first link tuple, the last segment data storage unit stores only the last, other memory cells are stored in a data segment and a link tuple. 通常情况下,存储单元链中的第一存储单元可以包括一个索引树的叶结点(逻辑主叶)中的信息,其它存储单元以平表中的元素的形式存储链接二元组和/或数据段,作为该叶节点的扩展。 Typically, the storage unit chain first storage unit may include a leaf node of the index tree (logical primary leaves) information, other memory cells in the form of a flat element link table stored tuples and / or data segment as an extension of the leaf node. 在这种情况下,所使用的链接二元组可以由一个平表标识符TID 和一个元素标识符EID组成,其中平表标识符TID指向的是下一个数据段所在平表的表号,而元素标识符EID指向的是该数据段所在平表的元素号或行号。 In this case, the link tuple identifier can be used by one meter and a TID identifier EID element, where the meter identifier TID number points to the next data segment table where the flat table, and EID element identifier pointing to the data segment is located the element number or the line number of the meter. 可以通过平表标识符TID和元素标识符EID 来访问平表中的元素。 Access elements may be flat table and TID identifier EID element identifier through the meter. 平表标识符TID和元素标识符EID都是用软件定义的元素。 Flat table identifier EID element identifier TID and the element are defined by software. 当开始一个任务时,处理引擎或处理器利用输入数据进行树查询。 When starting a task, processor or processing engine using data input query tree. 当出现匹配时,即找到合适的逻辑主叶时,根据需要,处理器可以利用链接二元组{TID, EID}读取逻辑扩展叶中的信息。 When a match occurs, i.e. the main lobe find suitable logic, if necessary, the processor may use the link-tuple {TID, EID} extended information is read logic leaves. 图2示出了根据本发明的一个优选实施方式的数据存储结构。 FIG 2 illustrates a data storage structure in accordance with a preferred embodiment of the present invention. 如图2所示,根据本发明的数据存储结构包括一个第一存储单元210 和一个第二存储单元220。 2, the data storage structure of the present invention comprises a first storage unit 210 and a second storage unit 220. 第一存储单元210包括一个第一数据段212和一个第一链接二元组214。 A first storage unit 210 includes a first section 212 and a data tuple 214 of the first link. 其中,该第一链接二元组214指向在第二存储单元220内包括的一个第二数据段222。 Wherein the first tuple 214 points to a link in the second memory unit 220 includes a second data segment 222. 例如,通过提供该第一链接二元组214,可以访问在第二存储单元"0中包括的该第二数据段222。第一存储单元210和第二存储单元可以在空间上不相邻,只要存在相应的逻辑关系,能够通过第一存储单元210中的该第一链接二元组214确定第二存储单元220内的第二数据段"2即可。 For example, by providing a link to the first tuple 214 can access data including the second segment 222. The first storage unit 210 and the second storage unit may not be spatially adjacent to the second storage unit, "0, As long as there is a corresponding logical relationship, the first storage unit 210 through the first link in the second data segments is determined tuple "in the second storage unit 214 to 2,202. 当然,本领域的技术人员应当理解,第一存储单元210可以只包括一个第一链接二元组214,而不包括第一数据段212。 Of course, those skilled in the art will appreciate, the first storage unit 210 may include only a link to a first tuple 214, the first data segment 212 does not include. 上述数据存储结构还可以包括一个第三存储单元(未示出),用于存储一个第三数据段。 The data storage structure may further include a third storage unit (not shown) for storing a third data segment. 在这种情况下,第二存储单元220中需要包括一个第二链接二元组,该第二链接二元组指向该第三数据段。 In this case, the second storage unit 220 needs to include a link to a second tuple, the tuple of the second link pointing to the third data segment. 本领域技术人员可以想到,该数据存储结构还可以包括第四、第五存储单元等,各个存储中包括相应的数据段。 Those skilled in the art can appreciate, the data storage structure may further include a fourth, a fifth memory unit or the like, each comprising a respective data storage segment. 所包括的存储单元的个数不构成对本发明的限制。 The number of memory cells included does not limit the present invention. 当然,本领域的技术人员应当理解,各个存储单元中可以只存储一个链接二元组,也可以根据需要存储多个链接二元组。 Of course, those skilled in the art will appreciate that each memory cell can store only one link in the tuple may be necessary to store a plurality of links according to the tuple. 图3示出了根据本发明的另一个实施方式的数据存储结构。 FIG 3 illustrates a data storage structure according to another embodiment of the present invention. 如图3所示,该数据存储结构包括多级存储单元(图中仅示出两级)。 As shown in FIG. 3, the data storage structure includes a multi-level memory cells (only two shown). 第一级存储单元310包括一个存储单元,第二级存储单元320包括N 个存储单元,第三级存储单元包括MxN个存储单元(未示出)。 The first stage comprises a storage unit 310 storing unit, a second-level storage unit 320 comprises N memory cells, the third-level memory cells comprises MxN memory cells (not shown). 第一级存储单元310包括N个链接二元组,分别指向分别存储在第二级存储单元320中的N个存储单元中的N个平表元素。 Level storage unit 310 includes a first N-tuple of links, each pointing to the N level table element from the second stage of the N storage unit 320 are respectively stored. 第二级存储单元320中的每一个存储单元包括M个链接二元组,分别指向分别存储在第三级存储单元中的M个存储单元中的M个平表元素。 Second level storage unit 320 in each of the memory cell M comprises a link tuple pointing to the M level memory cell element M tables are stored in the third stage in the storage unit. 上述各级存储单元根据需要还可以存储相应的数据段。 The storage unit according to the above-described levels required may also store the corresponding data segment. 这种级联机制在例如负载平衡等应用中非常有用(N和M为大于1 的正整数)。 This cascade mechanism is useful in applications such as, for example, load balancing (N and M are positive integers greater than 1). 显然,该新的数据链接机制(数据存储方法)能够提供特定处理器由于提高性能而丟失的链接能力。 Obviously, the new data link mechanisms (data storage method) can provide a specific processor to improve performance due to the lost link capacity. 该新的数据链接概念消除了存储器的物理限制(即,叶容量的物理限制)。 The novel concept eliminates the data link physical limitations of the memory (i.e., physical limitations leaf capacity). 本领域技术人员可以想到,所适用的数据结构不限于树的结构, 只要能够通过链接二元组将多各数据段链接在一起即可。 Those skilled in the art can appreciate, the applied data structure of the tree structure is not limited, as long as each of the plurality of data segments can be linked together through a connection tuple. 数据结构不构成对本发明的限制。 Data structure does not limit the present invention. 本领域的技术人员应当理解,上述数据段可以包括各种类型的数据,例如整型、浮点型、字符串型等等。 Those skilled in the art will appreciate that the data segments may comprise various types of data such as integers, floating point, string and the like. 根据本发明的优选实施方式的数据存储结构和数据存储方法可以应用于上述特定目的处理器,也可以应用于其他处理器。 The data storage method for storing data structures and preferred embodiment of the present invention may be applied to the specific purpose processor, it may also be applied to other processors. 所适用的处理器的种类不构成对本发明的限制。 Type processor applies not limit the present invention. 还需要注意,除非特别指出,否则这里描述的所有功能都可以用硬件或软件实现,或者通过硬件和软件的结合实现。 Note also that, unless specifically noted otherwise, all functions described herein may be implemented in hardware or software, or implemented by a combination of hardware and software. 总之,本发明的基本思想是通过链接二元组在不支持存储地址指针的特定目的处理器中提供数据链接,从而突破存储数据所需要的空间的限制,提高链接各个数据段的效率。 In summary, the basic idea of ​​the invention is to provide a data link that does not support a particular memory address pointers purpose processor through a link tuple to break out the required data storage space, the link efficiency of each data segment. 提供本发明的说明书的目的是为了说明和描述,而不是用来穷举或将本发明限制为所公开的形式。 Object of the invention is provided for purposes of illustration and description is to describe, and is not intended to be exhaustive or to limit the invention to the forms disclosed. 对本领域的普通技术人员而言, 许多修改和变更都是显而易见的。 To those of ordinary skill in the art, many modifications and variations will be apparent. 选择并描述实施方式是为了更好地解释本发明的原理及其实际应用,并使本领域普通技术人员明白, 在不脱离本发明精神的前提下,所有修改和变更均落入由权利要求所限定的本发明的保护范围之内。 Chosen and described in order to best explain the principles of the invention and its practical application, and those of ordinary skill in the art understand that, without departing from the spirit of the invention, all modifications and changes as fall within the appended claims within the scope of the invention as defined.

Claims (11)

  1. 1. 一种存储数据的方法,包括如下步骤: 在第一存储区设置一个第一数据节点; 在第二存储区设置一个第二数据节点; 其中,所述第二数据节点是构成第二存储区中至少一个平表中的一个第一平表的多个元素中的一个元素; 并且,所述设置第一数据节点的步骤包括在该节点中存储一个链接二元组,其包括一个表示所述第一平表的第一标识符和一个表示所述元素在第一平表中所处的行的第二标识符。 A method of storing data, comprising the steps of: providing a first node in a first data storage area; providing a second node in the second data storage area; wherein said second data storage node constituting a second a plurality of elements in the at least one flat region of the table a first flat table; and, the step of setting said first data storage node includes a link in the node-tuple, which includes a representative of the a first table identifier and said first level represents the first planar element is located in the second identifier table row.
  2. 2. 如权利要求l所述的方法,进一步包含:在第一数据节点中与所述链接二元组一起存储一个数据。 2. The method according to claim l, further comprising: storing a link to the data tuple with the first data node.
  3. 3. 如权利要求1或2所述的方法,其中,设置第二数据节点的步骤进一步包含:在第二数据节点中存储至少一个链接二元组,每个链接二元组包括一个表示至少一个平表中的一个第二平表的第一标识符和一个表示第二平表中的多个元素中的一个元素的第二标识符。 3. The method of claim 1 or claim 2, wherein the step of setting a second data node further comprising: in the second data storage node tuple at least one link, each link comprising a tuple representing at least one first identifier of one meter and a second meter of the second identifier represents a second level of a plurality of elements in the table.
  4. 4. 如权利要求1或2所述的方法,其中,设置第二数据节点的步骤进一步包含:在第二数据节点中存储一个数据。 4. The method of claim 1 or claim 2, wherein the step of setting a second data node further comprises: storing data in a second data node.
  5. 5. 如权利要求3所述的方法,其中,设置第二数据节点的步骤进一步包含:在第二数据节点中存储一个数据。 5. The method according to claim 3, wherein the step of setting a second data node further comprises: storing data in a second data node.
  6. 6. 如权利要求3所述的方法,其中,笫二平表与第一平表是同一个平表。 6. The method according to claim 3, wherein the first table and the undertaking of the second level is the same level meter level meter.
  7. 7. 如权利要求4所述的方法,其中,第二平表与第一平表是同一个平表。 7. The method according to claim 4, wherein the first table and the second level is the same level meter level meter.
  8. 8. 如权利要求5所述的方法,其中,第二平表与第一平表是同一个平表。 8. A method as claimed in claim 5, wherein the first table and the second level is the same level meter level meter.
  9. 9. 如权利要求3所述的方法,其中,第二平表与第一平表不同。 9. The method as claimed in claim 3, wherein the first table and the second level different from the level meter.
  10. 10. 如权利要求4所述的方法,其中,第二平表与第一平表不同。 10. The method as claimed in claim 4, wherein the first table and the second level different from the level meter.
  11. 11. 如权利要求5所述的方法,其中,第二平表与第一平表不同。 11. The method according to claim 5, wherein the first table and the second level different from the level meter.
CN 200510097937 2005-08-31 2005-08-31 Data storage method and data storage structure CN100418090C (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 200510097937 CN100418090C (en) 2005-08-31 2005-08-31 Data storage method and data storage structure

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
CN 200510097937 CN100418090C (en) 2005-08-31 2005-08-31 Data storage method and data storage structure
US11513475 US20070050326A1 (en) 2005-08-31 2006-08-31 Data Storage method and data storage structure
US12139128 US8055681B2 (en) 2005-08-31 2008-06-13 Data storage method and data storage structure

Publications (2)

Publication Number Publication Date
CN1924851A true CN1924851A (en) 2007-03-07
CN100418090C true CN100418090C (en) 2008-09-10

Family

ID=37805555

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 200510097937 CN100418090C (en) 2005-08-31 2005-08-31 Data storage method and data storage structure

Country Status (2)

Country Link
US (2) US20070050326A1 (en)
CN (1) CN100418090C (en)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8909676B1 (en) * 2006-10-06 2014-12-09 Uei Cayman Inc. Star cluster codeset database for universal remote control devices
US8933105B2 (en) 2007-02-28 2015-01-13 Takeda Pharmaceutical Company Limited Pyrrole compounds
CN101354270B (en) 2008-05-05 2010-06-02 国网南京自动化研究院;南京南瑞集团公司 Method for storing electric power scheduling mass data
US8200930B2 (en) 2008-10-14 2012-06-12 Digital Lifeboat, Inc. Interacting with data in hidden storage
US20100100587A1 (en) * 2008-10-14 2010-04-22 Digital Lifeboat, Inc. Systems and methods for a data management recovery in a peer-to-peer network
WO2011145114A3 (en) * 2010-05-19 2012-03-08 Kamlesh Gandhi Composition of data objects
CN103326958B (en) * 2012-03-22 2017-07-04 罗普特(厦门)科技集团有限公司 Monitoring data caching method and system
WO2014174380A3 (en) 2013-04-22 2015-02-26 Bacula Systems Sa Creating a universally deduplicatable archive volume
US20160147779A1 (en) * 2014-11-26 2016-05-26 Microsoft Technology Licensing, Llc. Systems and Methods for Providing Distributed Tree Traversal Using Hardware-Based Processing

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6185569B2 (en)
US6185569B1 (en) 1998-06-29 2001-02-06 Microsoft Corporation Linked data structure integrity verification system which verifies actual node information with expected node information stored in a table
JP2001117929A (en) 1999-10-15 2001-04-27 Toshiba Corp Data retrieving method, data aligning method and data retrieving device
CN1383646A (en) 2000-04-06 2002-12-04 索尼公司 Information processing system and method
CN1411642A (en) 2000-11-09 2003-04-16 索尼公司 Information processing device, information processing method and program storage
GB2386978A (en) 2002-03-25 2003-10-01 Sony Uk Ltd Data structure
CN1462004A (en) 2002-05-31 2003-12-17 思科技术公司 Method and device for producing and using improved tree-shape bit map data structure

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5325325A (en) * 1990-03-30 1994-06-28 Sharp Kabushiki Kaisha Semiconductor memory device capable of initializing storage data
US5530854A (en) * 1992-09-25 1996-06-25 At&T Corp Shared tuple method and system for generating keys to access a database
US6049802A (en) * 1994-06-27 2000-04-11 Lockheed Martin Corporation System and method for generating a linked list in a computer memory
US6230151B1 (en) * 1998-04-16 2001-05-08 International Business Machines Corporation Parallel classification for data mining in a shared-memory multiprocessor system
US6334125B1 (en) * 1998-11-17 2001-12-25 At&T Corp. Method and apparatus for loading data into a cube forest data structure
US6721723B1 (en) * 1999-12-23 2004-04-13 1St Desk Systems, Inc. Streaming metatree data structure for indexing information in a data base
US7117217B2 (en) * 2000-05-15 2006-10-03 National University Of Singapore Apparatus and method for performing transformation-based indexing of high-dimensional data
EP1217541A1 (en) * 2000-11-29 2002-06-26 Lafayette Software Inc. Method of processing queries in a database system, and database system and software product for implementing such method
US6714943B1 (en) * 2001-01-31 2004-03-30 Oracle International Corporation Method and mechanism for tracking dependencies for referential integrity constrained tables
US6732116B2 (en) * 2001-06-21 2004-05-04 International Business Machines Corporation Method and system for dynamically managing data structures to optimize computer network performance
EP1423957A1 (en) * 2001-08-29 2004-06-02 Nokia Corporation Method and system for classifying binary strings
US6785674B2 (en) * 2003-01-17 2004-08-31 Intelitrac, Inc. System and method for structuring data in a computer system

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6185569B2 (en)
US6185569B1 (en) 1998-06-29 2001-02-06 Microsoft Corporation Linked data structure integrity verification system which verifies actual node information with expected node information stored in a table
JP2001117929A (en) 1999-10-15 2001-04-27 Toshiba Corp Data retrieving method, data aligning method and data retrieving device
CN1383646A (en) 2000-04-06 2002-12-04 索尼公司 Information processing system and method
CN1411642A (en) 2000-11-09 2003-04-16 索尼公司 Information processing device, information processing method and program storage
GB2386978A (en) 2002-03-25 2003-10-01 Sony Uk Ltd Data structure
CN1462004A (en) 2002-05-31 2003-12-17 思科技术公司 Method and device for producing and using improved tree-shape bit map data structure

Also Published As

Publication number Publication date Type
CN1924851A (en) 2007-03-07 application
US20070050326A1 (en) 2007-03-01 application
US20080281773A1 (en) 2008-11-13 application
US8055681B2 (en) 2011-11-08 grant

Similar Documents

Publication Publication Date Title
Andersen et al. FAWN: A fast array of wimpy nodes
Risson et al. Survey of research towards robust peer-to-peer networks: Search methods
Lloyd et al. Stronger Semantics for Low-Latency Geo-Replicated Storage.
Abraham et al. Performance of the direct binary n-cube network for multiprocessors
Tang et al. Coordinated en-route web caching
Lim et al. SILT: A memory-efficient, high-performance key-value store
US20120030477A1 (en) Scalable segment-based data de-duplication system and method for incremental backups
US7043494B1 (en) Fast, deterministic exact match look-ups in large tables
Basu et al. Fast incremental updates for pipelined forwarding engines
US20030048785A1 (en) Network processor with single interface supporting tree search engine and CAM
US8051362B2 (en) Distributed data storage using erasure resilient coding
US7644080B2 (en) Method and apparatus for managing multiple data flows in a content search system
US20130218840A1 (en) System and method for building a point-in-time snapshot of an eventually-consistent data store
US20060218167A1 (en) Systems, methods and programming for routing and indexing globally addressable objects and associated business models
US5166674A (en) Multiprocessing packet switching connection system having provision for error correction and recovery
Leighton et al. Expanders might be practical: Fast algorithms for routing around faults on multibutterflies
US7529746B2 (en) Search circuit having individually selectable search engines
US20060041715A1 (en) Multiprocessor chip having bidirectional ring interconnect
Sistare et al. Optimization of MPI collectives on clusters of large-scale SMP's
US7146371B2 (en) Performance and memory bandwidth utilization for tree searches using tree fragmentation
US20080046445A1 (en) Systems and methods of reverse lookup
Zhu et al. Hba: Distributed metadata management for large cluster-based storage systems
US20080229056A1 (en) Method and apparatus for dual-hashing tables
Nightingale et al. Flat Datacenter Storage.
US6754776B2 (en) Method and system for logical partitioning of cache memory structures in a partitoned computer system

Legal Events

Date Code Title Description
C06 Publication
C10 Entry into substantive examination
C14 Grant of patent or utility model
CF01